Enhancing human intelligence with neurofeedback

I think trying to give a BCI product to AI Safety researcher is unlikely to make ai safety researchers much smarter than the rest, and don't see it scaling faster than other general BCIs. Lacks empirical exploration.

The idea for the underlying is interesting, but also wasnt developed during the last weekend, and there is no demo/simulation. Would also somehow question if the "fooling oneself" is that much of an issue for researchers. I would imagine that this tech would be used for many other things, before being useful for detecting whether researchers are fooling themselves -> Please prove me wrong, I would love to have this not be the case. More straight forward path would probably to do BCI work in order to to come up with new mech interp approaches, but maybe this will become a byproduct further down the line. Obviously big dual use risk here.

Interesting application of BCI! Curious about why you chose to focus on fNIRS in particular - the line of reasoning for this does not seem to be convincingly developed in your write-up. Given its effectiveness as a feedback modality is still a matter of debate due to its low spatial resolution and inconsistent signal quality amongst other concerns, it would be interesting to compare to alternative approaches (EEG/TMS/ECoG etc). It would also be valuable to think through the current competitive landscape in the space a bit more thoroughly, along with methodology both in terms of technical implementation and go-to-market strategy.